{ "add_expanded_embeddings": true, "architectures": [ "BolmoForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_bolmo.BolmoConfig", "AutoModelForCausalLM": "modeling_bolmo.BolmoForCausalLM" }, "bos_token_id": 1, "boundary_predictor_lookahead": 1, "boundary_threshold": "sample:0", "dtype": "float32", "eos_token_id": 1, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "local_intermediate_size": 2816, "local_rms_norm_eps": 1e-05, "max_position_embeddings": 65536, "model_type": "bolmo", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 16, "num_local_decoder_layers": 4, "num_local_encoder_layers": 1, "num_local_heads": 16, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 500000.0, "sliding_window": 4096, "subword_vocab_size": 100278, "tie_word_embeddings": false, "tokenizer_config": { "bos_token_id": 1, "bpe_token_end_id": 3, "eos_token_id": 1, "original_identifier": "allenai/dolma2-tokenizer", "pad_token_id": 0, "special_tokens": [ "", "", "", "" ], "special_tokens_first": true, "vocab_size": 520 }, "transformers_version": "4.57.3", "use_cache": true, "vocab_size": 520 }